This paper describes on-line recognition of handwritten Lao characters by adopting Markov random field (MRF). The character set to recognize includes consonants, vowels and tone marks, 52 characters in total. It extracts feature points along the pen-tip trace from pen-down to pen-up, and then sets each feature point from an input pattern as a site and each state from a character class as a label. It recognizes an input pattern by using a linear-chain MRF model to assign labels to the sites of the input pattern. It employs the coordinates of feature points as unary features and the transitions of the coordinates between the neighboring feature points as binary features. An evaluation on the Lao character pattern database demonstrates the robustness of our proposed method with recognition rate of 92.41% and respectable recognition time of less than a second per character.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Latsamy SAYSOURINHONG, Bilan ZHU, Masaki NAKAGAWA, "Online Handwritten Lao Character Recognition by MRF" in IEICE TRANSACTIONS on Information,
vol. E95-D, no. 6, pp. 1603-1609, June 2012, doi: 10.1587/transinf.E95.D.1603.
Abstract: This paper describes on-line recognition of handwritten Lao characters by adopting Markov random field (MRF). The character set to recognize includes consonants, vowels and tone marks, 52 characters in total. It extracts feature points along the pen-tip trace from pen-down to pen-up, and then sets each feature point from an input pattern as a site and each state from a character class as a label. It recognizes an input pattern by using a linear-chain MRF model to assign labels to the sites of the input pattern. It employs the coordinates of feature points as unary features and the transitions of the coordinates between the neighboring feature points as binary features. An evaluation on the Lao character pattern database demonstrates the robustness of our proposed method with recognition rate of 92.41% and respectable recognition time of less than a second per character.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E95.D.1603/_p
Copy
@ARTICLE{e95-d_6_1603,
author={Latsamy SAYSOURINHONG, Bilan ZHU, Masaki NAKAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Online Handwritten Lao Character Recognition by MRF},
year={2012},
volume={E95-D},
number={6},
pages={1603-1609},
abstract={This paper describes on-line recognition of handwritten Lao characters by adopting Markov random field (MRF). The character set to recognize includes consonants, vowels and tone marks, 52 characters in total. It extracts feature points along the pen-tip trace from pen-down to pen-up, and then sets each feature point from an input pattern as a site and each state from a character class as a label. It recognizes an input pattern by using a linear-chain MRF model to assign labels to the sites of the input pattern. It employs the coordinates of feature points as unary features and the transitions of the coordinates between the neighboring feature points as binary features. An evaluation on the Lao character pattern database demonstrates the robustness of our proposed method with recognition rate of 92.41% and respectable recognition time of less than a second per character.},
keywords={},
doi={10.1587/transinf.E95.D.1603},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Online Handwritten Lao Character Recognition by MRF
T2 - IEICE TRANSACTIONS on Information
SP - 1603
EP - 1609
AU - Latsamy SAYSOURINHONG
AU - Bilan ZHU
AU - Masaki NAKAGAWA
PY - 2012
DO - 10.1587/transinf.E95.D.1603
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E95-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2012
AB - This paper describes on-line recognition of handwritten Lao characters by adopting Markov random field (MRF). The character set to recognize includes consonants, vowels and tone marks, 52 characters in total. It extracts feature points along the pen-tip trace from pen-down to pen-up, and then sets each feature point from an input pattern as a site and each state from a character class as a label. It recognizes an input pattern by using a linear-chain MRF model to assign labels to the sites of the input pattern. It employs the coordinates of feature points as unary features and the transitions of the coordinates between the neighboring feature points as binary features. An evaluation on the Lao character pattern database demonstrates the robustness of our proposed method with recognition rate of 92.41% and respectable recognition time of less than a second per character.
ER -